GET

/v1/schemas/zai/image/paas/v4/images/generations

Accept:

kind inputactivity imagehash 8153c724…extracted Oct 11, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `7f6180b5813f06e7d34566471e85f0ebbe024fcf39a9bd79c7034f3c4b4de638` { "fetchedAt": 1791696079, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 2 required · 0 $defs

property	type	description	constraints
model*	enum	Model code	glm-image
prompt*	string	The text description of the image to be generated.
quality	enum	The quality of the generated image. `glm-image` default is `hd`, others model is `standard`. `hd`: Generates a more detailed and rich image with higher overall consistency, but takes about `20` seconds. `standard`: Generates an image quickly, suitable for scen…	hd \| standard · default: "hd"
size	string	Image size. `glm-image` recommended enum values: `1280x1280` (default), `1568x1056`, `1056x1568`, `1472x1088`, `1088x1472`, `1728x960`, `960x1728`. Custom parameter: Both width and height must be between `1024px-2048px`, and must be divisible by `32`, and the …	default: "1280x1280"
user_id	string	Unique ID of the end user, helping the platform intervene in illegal activities, inappropriate content generation, or other abuses. ID length: 6 to 128 characters.	length ≥ 6 · length ≤ 128

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"zai","endpointId":"paas/v4/images/generations","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}